Hugging Face's logo

jssky
/
f57094e1-f78a-4efa-8c1e-9094b2d96b16

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
f57094e1-f78a-4efa-8c1e-9094b2d96b16
File size: 3,061 Bytes 
f5ee420
 
 
4a1dc21
f5ee420
4a1dc21
f5ee420
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99f58fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4a1dc21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f5ee420
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4a1dc21
f5ee420
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005432322317790856,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006035913686434284,
      "grad_norm": 0.009034841321408749,
      "learning_rate": 2e-05,
      "loss": 11.9322,
      "step": 1
    },
    {
      "epoch": 0.0006035913686434284,
      "eval_loss": 11.93203353881836,
      "eval_runtime": 9.6604,
      "eval_samples_per_second": 288.912,
      "eval_steps_per_second": 36.127,
      "step": 1
    },
    {
      "epoch": 0.0012071827372868568,
      "grad_norm": 0.009666570462286472,
      "learning_rate": 4e-05,
      "loss": 11.933,
      "step": 2
    },
    {
      "epoch": 0.0018107741059302852,
      "grad_norm": 0.008490069769322872,
      "learning_rate": 6e-05,
      "loss": 11.932,
      "step": 3
    },
    {
      "epoch": 0.0018107741059302852,
      "eval_loss": 11.932022094726562,
      "eval_runtime": 9.7136,
      "eval_samples_per_second": 287.329,
      "eval_steps_per_second": 35.929,
      "step": 3
    },
    {
      "epoch": 0.0024143654745737136,
      "grad_norm": 0.010773689486086369,
      "learning_rate": 8e-05,
      "loss": 11.9312,
      "step": 4
    },
    {
      "epoch": 0.003017956843217142,
      "grad_norm": 0.009934109635651112,
      "learning_rate": 0.0001,
      "loss": 11.931,
      "step": 5
    },
    {
      "epoch": 0.0036215482118605704,
      "grad_norm": 0.010047477670013905,
      "learning_rate": 0.00012,
      "loss": 11.9307,
      "step": 6
    },
    {
      "epoch": 0.0036215482118605704,
      "eval_loss": 11.93198299407959,
      "eval_runtime": 9.7077,
      "eval_samples_per_second": 287.503,
      "eval_steps_per_second": 35.951,
      "step": 6
    },
    {
      "epoch": 0.004225139580503999,
      "grad_norm": 0.008809824474155903,
      "learning_rate": 0.00014,
      "loss": 11.9323,
      "step": 7
    },
    {
      "epoch": 0.004828730949147427,
      "grad_norm": 0.00893594790250063,
      "learning_rate": 0.00016,
      "loss": 11.9324,
      "step": 8
    },
    {
      "epoch": 0.005432322317790856,
      "grad_norm": 0.011988944374024868,
      "learning_rate": 0.00018,
      "loss": 11.9309,
      "step": 9
    },
    {
      "epoch": 0.005432322317790856,
      "eval_loss": 11.931912422180176,
      "eval_runtime": 9.7178,
      "eval_samples_per_second": 287.206,
      "eval_steps_per_second": 35.914,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 53961818112.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}